The technology behind GPT Image 2.6
How the model works, based on public documentation and sourced evidence.
OpenAI released Images 2.6 on 4 November 2026. The API exposes gpt-image-2.6-flare and gpt-image-2.6-sunburst. Both generate and edit images from text and image inputs. OpenAI positions Flare for rapid iteration and Sunburst for detailed visual work; these are the developer's stated roles, not a Vidney benchmark result.
The official Image API adds complexity control, markup-guided edits, SVG output and native animated GIF output for the 2.6 family. GIF output belongs to POST /v1/images/generations. OpenAI's guide explicitly says the image edit endpoint does not support GIF output.
On Vidney, the model page combines Flare and Sunburst for text-to-image and image-to-image work. Its current generator returns static PNG images at 1K in 1:1, 4:3, 3:4, 16:9 or 9:16, with quality fixed to medium. The generation button shows the current credit cost.
Use identical prompts and settings when comparing GPT Image 2.6 with GPT Image 2.5. Review text, identity details and product geometry in each output before using it. Higher resolutions, transparent backgrounds, SVG exports and markup controls are outside this page's current generator.